Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e089f1fe044a7210e069a3134f30f019c3f51d0db0b7191372f69c58a4dbbfa
+oid sha256:18aabee0dc55a57ca5b9c7d078bdb1dd84467c5c4f5695e37a0c34b7f8a72dae
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15313b8b93f0186952bf252d80322771ebad5137380b60c17726216f4d5d6710
+oid sha256:833dfbd830adb0324c091c0ebdd93f2046d2295b7aeb20ada9cbfc2ed0b19da0
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ba74afa0c42946643885d2bdc990f5514233d2f80bbe5a0e8ba5ba52d2fd479
+oid sha256:27c3d82662ec60d2e3a95ca5780f67f4054aa4789931959462842bbb87c79e23
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
+oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04213938411669368,
+  "epoch": 0.06320907617504051,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 58.387,
       "eval_steps_per_second": 29.193,
       "step": 26
+    },
+    {
+      "epoch": 0.04862236628849271,
+      "grad_norm": 0.9814926981925964,
+      "learning_rate": 0.0001,
+      "loss": 3.2828,
+      "step": 30
+    },
+    {
+      "epoch": 0.06320907617504051,
+      "eval_loss": 3.4281005859375,
+      "eval_runtime": 4.4556,
+      "eval_samples_per_second": 58.353,
+      "eval_steps_per_second": 29.177,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 241679978201088.0,
+  "total_flos": 352929491976192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null